https://zulfaqarhafez.com/notes Short technical notes from the work: measurements, figures and negative results. en https://zulfaqarhafez.com/notes/the-fix-that-cost-tokens https://zulfaqarhafez.com/notes/the-fix-that-cost-tokens Tue, 13 Oct 2026 00:00:00 GMT TraceRazor measured its own patch on 12 live coding runs and found it raised token use by 5.6 percent instead of cutting it. What the rerun gate caught, what changed, and why a second round centred on zero was the right answer. https://zulfaqarhafez.com/notes/what-the-pond-teaches https://zulfaqarhafez.com/notes/what-the-pond-teaches Tue, 13 Oct 2026 00:00:00 GMT The koi pond on the home page is a toy with real failure modes: a noisy detector, a confirmation gate, a tracker that loses IDs under occlusion, and a count that drifts up, which re-identification cuts by about four fifths. https://zulfaqarhafez.com/notes/pre-registering-a-no https://zulfaqarhafez.com/notes/pre-registering-a-no Tue, 13 Oct 2026 00:00:00 GMT OsciWriting fixed one rule before the decision run: if judged substitutability missed a 70 percent bar, the answer was Abandon. It came in at 12.8 to 15.3 percent. What was locked in advance, what was not, and why the verdict holds either way. https://zulfaqarhafez.com/notes/why-one-pass-never-certifies-an-agent https://zulfaqarhafez.com/notes/why-one-pass-never-certifies-an-agent Tue, 13 Oct 2026 00:00:00 GMT Assay gates its verdicts at pass^k on held-out probes. The arithmetic behind that rule, what a deterministic demo can and cannot show, and why a mean of 0.80 across categories still failed.